Skip to content

InferHaven/agent-skills / codetrain

codetrain

Flagged

CodeTrain is an open-source Socratic coding tutor with a local lesson page where the learner writes every line while the agent sets small steps, gives hints and reviews the work without putting the solution into the lesson. Use when the user wants to be taught/walked through code one tiny step at a time — triggers like "teach me this code", "walk me through this", "hold my hand", "explain step by step", "tutor me", "guide me through", "I want to learn this", or asks for a safe practice exercise to learn a concept.

FileKindSize
LICENSEother11.1 KB
NOTICEother768 B
README.mdmarkdown22.7 KB
SKILL.mdskill md20.1 KB
app/answer_guard.pyscript7.8 KB
app/checkpoint-hook.shexecutablescript1.2 KB
app/ctl.shexecutablescript4.5 KB
app/install-permissions.pyscript6.8 KB
app/patch.pyexecutablescript4.1 KB
app/profile.pyexecutablescript9.3 KB
app/server.pyexecutablescript23.1 KB
app/static/Archivo.woff2binary88.0 KB
app/static/JetBrainsMono.woff2binary30.7 KB
app/static/app.jsscript57.1 KB
app/static/docklint.jsscript4.3 KB
app/static/editor.jsscript4.4 KB
app/static/fonts-OFL.txtmarkdown9.0 KB
app/static/glossary.jsscript50.8 KB
app/static/index.htmlother8.0 KB
app/static/js-worker.jsscript3.9 KB
app/static/liveness.jsscript1.8 KB
app/static/logo-anim.svgother1.9 KB
app/static/prism.jsscript20.6 KB
app/static/prose.jsscript18.8 KB
app/static/pyodide-worker.jsscript7.0 KB
app/static/runner.jsscript4.5 KB
app/static/sheet.cssother32.7 KB
app/static/styles.cssother51.4 KB
app/static/theme-toggle.jsscript9.5 KB
app/static/theme.jsscript5.2 KB
app/static/visuals.jsscript14.8 KB
app/watch.shexecutablescript2.5 KB
install.shexecutablescript2.0 KB
references/session-protocol.mdmarkdown19.6 KB
references/spaced-repetition.mdmarkdown3.4 KB
references/teach-on-diff.mdmarkdown2.5 KB

references/teach-on-diff.md

View on GitHub
# Teach-on-diff (learn from real changes, Socratically)

A local-code variant: instead of inventing an exercise, the tutor turns a **real
diff** — the learner's own uncommitted work, a commit, a branch, or a PR — into a
hands-on walkthrough. The learner re-derives each change themselves; you never paste
the finished diff as the answer (the one hard rule still holds).

## Triggers

"teach me this diff", "walk me through these changes / this PR", "review my diff
Socratically", "explain what I just changed", "quiz me on this PR".

## Get the material (read-only)

Pick the source with the user, then read it with your own tools:

- Their uncommitted work — `git diff` (unstaged) · `git diff --staged` · `git diff HEAD`
- A commit / range / branch — `git diff <base>..<head>` · `git diff main...feature` ·
  `git show <sha>`
- A GitHub PR — `gh pr diff <n>` if `gh` is installed and authed, else fetch the
  branch and `git diff`.

`git diff` is in the prompt-free allow-list; `git show` / `gh` may prompt once at
setup. Read the diff — do **not** paste it wholesale into the lesson.

## Author the lesson

Group the diff into the few **meaningful** hunks (skip noise: formatting, lockfiles,
generated files). For each, author one step:

- `body_md` — the context and the **why**: what problem this change addresses and the
  concept it exercises (a guard added, an API swapped, a loop made lazy, a bug fixed…).
- `starter_code` — the **before-state** of that area (the pre-change lines), or the
  surrounding code with the changed part left as a `# TODO`. **Never the after-state.**
- `task_md` — ask the learner to **produce the change themselves**: reimplement the
  hunk; or, for changes that aren't reproducible exercises (deletions, renames,
  config), **explain** what it does, why it's there, and what would break without it.
- Review against the real after-state (you know it): Socratic feedback, nudge toward
  the actual approach, ask them to justify the trade-off — but never reveal the
  finished lines.

## Mode

- **Their own change, still in the tree** → working on the real file is fine, but seed the editor
  from the *before-state* so they re-derive it; their working tree stays untouched
  until they choose to keep it.
- **A PR or someone else's commit** → use **sandbox** mode (a throwaway copy of the
  before-state) so the exercise never touches their files. Say so plainly.

End and save progress as usual; log any concept they fumbled as a **gap** for spaced
repetition — see `references/spaced-repetition.md`.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall